© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70380
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vlastnosti
    -1.23
    ellä
    -1.22
    mitives
    -1.21
    ﻻ
    -1.21
    مقدمه
    -1.20
    ช่วง
    -1.20
    揄
    -1.20
    ellites
    -1.20
    鬟
    -1.20
    )}_
    -1.19
    POSITIVE LOGITS
     we
    1.68
     this
    1.37
     things
    1.32
     If
    1.30
     you
    1.29
    It
    1.27
     our
    1.24
     one
    1.24
     each
    1.23
     would
    1.20
    Activations Density 0.208%

    No Known Activations